Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking update from David Miller:

 1) Checkpoint/restarted TCP sockets now can properly propagate the TCP
    timestamp offset.  From Andrey Vagin.

 2) VMWARE VM VSOCK layer, from Andy King.

 3) Much improved support for virtual functions and SR-IOV in bnx2x,
    from Ariel ELior.

 4) All protocols on ipv4 and ipv6 are now network namespace aware, and
    all the compatability checks for initial-namespace-only protocols is
    removed.  Thanks to Tom Parkin for helping deal with the last major
    holdout, L2TP.

 5) IPV6 support in netpoll and network namespace support in pktgen,
    from Cong Wang.

 6) Multiple Registration Protocol (MRP) and Multiple VLAN Registration
    Protocol (MVRP) support, from David Ward.

 7) Compute packet lengths more accurately in the packet scheduler, from
    Eric Dumazet.

 8) Use per-task page fragment allocator in skb_append_datato_frags(),
    also from Eric Dumazet.

 9) Add support for connection tracking labels in netfilter, from
    Florian Westphal.

10) Fix default multicast group joining on ipv6, and add anti-spoofing
    checks to 6to4 and 6rd.  From Hannes Frederic Sowa.

11) Make ipv4/ipv6 fragmentation memory limits more reasonable in modern
    times, rearrange inet frag datastructures for better cacheline
    locality, and move more operations outside of locking.  From Jesper
    Dangaard Brouer.

12) Instead of strict master <--> slave relationships, allow arbitrary
    scenerios with "upper device lists".  From Jiri Pirko.

13) Improve rate limiting accuracy in TBF and act_police, also from Jiri
    Pirko.

14) Add a BPF filter netfilter match target, from Willem de Bruijn.

15) Orphan and delete a bunch of pre-historic networking drivers from
    Paul Gortmaker.

16) Add TSO support for GRE tunnels, from Pravin B SHelar.  Although
    this still needs some minor bug fixing before it's %100 correct in
    all cases.

17) Handle unresolved IPSEC states like ARP, with a resolution packet
    queue.  From Steffen Klassert.

18) Remove TCP Appropriate Byte Count support (ABC), from Stephen
    Hemminger.  This was long overdue.

19) Support SO_REUSEPORT, from Tom Herbert.

20) Allow locking a socket BPF filter, so that it cannot change after a
    process drops capabilities.

21) Add VLAN filtering to bridge, from Vlad Yasevich.

22) Bring ipv6 on-par with ipv4 and do not cache neighbour entries in
    the ipv6 routes, from YOSHIFUJI Hideaki.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1538 commits)
  ipv6: fix race condition regarding dst->expires and dst->from.
  net: fix a wrong assignment in skb_split()
  ip_gre: remove an extra dst_release()
  ppp: set qdisc_tx_busylock to avoid LOCKDEP splat
  atl1c: restore buffer state
  net: fix a build failure when !CONFIG_PROC_FS
  net: ipv4: fix waring -Wunused-variable
  net: proc: fix build failed when procfs is not configured
  Revert "xen: netback: remove redundant xenvif_put"
  net: move procfs code to net/core/net-procfs.c
  qmi_wwan, cdc-ether: add ADU960S
  bonding: set sysfs device_type to 'bond'
  bonding: fix bond_release_all inconsistencies
  b44: use netdev_alloc_skb_ip_align()
  xen: netback: remove redundant xenvif_put
  net: fec: Do a sanity check on the gpio number
  ip_gre: propogate target device GSO capability to the tunnel device
  ip_gre: allow CSUM capable devices to handle packets
  bonding: Fix initialize after use for 3ad machine state spinlock
  bonding: Fix race condition between bond_enslave() and bond_3ad_update_lacp_rate()
  ...

1 files changed, 705 insertions, 160 deletions

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 31cfe2ec75df..ed79a1c53b59 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -1,7 +1,7 @@
 /*******************************************************************************
 
   Intel(R) Gigabit Ethernet Linux driver
-  Copyright(c) 2007-2012 Intel Corporation.
+  Copyright(c) 2007-2013 Intel Corporation.
 
   This program is free software; you can redistribute it and/or modify it
   under the terms and conditions of the GNU General Public License,
@@ -57,6 +57,7 @@
 #ifdef CONFIG_IGB_DCA
 #include <linux/dca.h>
 #endif
+#include <linux/i2c.h>
 #include "igb.h"
 
 #define MAJ 4
@@ -68,7 +69,8 @@ char igb_driver_name[] = "igb";
 char igb_driver_version[] = DRV_VERSION;
 static const char igb_driver_string[] =
 				"Intel(R) Gigabit Ethernet Network Driver";
-static const char igb_copyright[] = "Copyright (c) 2007-2012 Intel Corporation.";
+static const char igb_copyright[] =
+				"Copyright (c) 2007-2013 Intel Corporation.";
 
 static const struct e1000_info *igb_info_tbl[] = {
 	[board_82575] = &e1000_82575_info,
@@ -193,6 +195,7 @@ static const struct dev_pm_ops igb_pm_ops = {
 };
 #endif
 static void igb_shutdown(struct pci_dev *);
+static int igb_pci_sriov_configure(struct pci_dev *dev, int num_vfs);
 #ifdef CONFIG_IGB_DCA
 static int igb_notify_dca(struct notifier_block *, unsigned long, void *);
 static struct notifier_block dca_notifier = {
@@ -234,6 +237,7 @@ static struct pci_driver igb_driver = {
 	.driver.pm = &igb_pm_ops,
 #endif
 	.shutdown = igb_shutdown,
+	.sriov_configure = igb_pci_sriov_configure,
 	.err_handler = &igb_err_handler
 };
 
@@ -565,6 +569,91 @@ exit:
 	return;
 }
 
+/*  igb_get_i2c_data - Reads the I2C SDA data bit
+ *  @hw: pointer to hardware structure
+ *  @i2cctl: Current value of I2CCTL register
+ *
+ *  Returns the I2C data bit value
+ */
+static int igb_get_i2c_data(void *data)
+{
+	struct igb_adapter *adapter = (struct igb_adapter *)data;
+	struct e1000_hw *hw = &adapter->hw;
+	s32 i2cctl = rd32(E1000_I2CPARAMS);
+
+	return ((i2cctl & E1000_I2C_DATA_IN) != 0);
+}
+
+/* igb_set_i2c_data - Sets the I2C data bit
+ *  @data: pointer to hardware structure
+ *  @state: I2C data value (0 or 1) to set
+ *
+ *  Sets the I2C data bit
+ */
+static void igb_set_i2c_data(void *data, int state)
+{
+	struct igb_adapter *adapter = (struct igb_adapter *)data;
+	struct e1000_hw *hw = &adapter->hw;
+	s32 i2cctl = rd32(E1000_I2CPARAMS);
+
+	if (state)
+		i2cctl |= E1000_I2C_DATA_OUT;
+	else
+		i2cctl &= ~E1000_I2C_DATA_OUT;
+
+	i2cctl &= ~E1000_I2C_DATA_OE_N;
+	i2cctl |= E1000_I2C_CLK_OE_N;
+	wr32(E1000_I2CPARAMS, i2cctl);
+	wrfl();
+
+}
+
+/* igb_set_i2c_clk - Sets the I2C SCL clock
+ *  @data: pointer to hardware structure
+ *  @state: state to set clock
+ *
+ *  Sets the I2C clock line to state
+ */
+static void igb_set_i2c_clk(void *data, int state)
+{
+	struct igb_adapter *adapter = (struct igb_adapter *)data;
+	struct e1000_hw *hw = &adapter->hw;
+	s32 i2cctl = rd32(E1000_I2CPARAMS);
+
+	if (state) {
+		i2cctl |= E1000_I2C_CLK_OUT;
+		i2cctl &= ~E1000_I2C_CLK_OE_N;
+	} else {
+		i2cctl &= ~E1000_I2C_CLK_OUT;
+		i2cctl &= ~E1000_I2C_CLK_OE_N;
+	}
+	wr32(E1000_I2CPARAMS, i2cctl);
+	wrfl();
+}
+
+/* igb_get_i2c_clk - Gets the I2C SCL clock state
+ *  @data: pointer to hardware structure
+ *
+ *  Gets the I2C clock state
+ */
+static int igb_get_i2c_clk(void *data)
+{
+	struct igb_adapter *adapter = (struct igb_adapter *)data;
+	struct e1000_hw *hw = &adapter->hw;
+	s32 i2cctl = rd32(E1000_I2CPARAMS);
+
+	return ((i2cctl & E1000_I2C_CLK_IN) != 0);
+}
+
+static const struct i2c_algo_bit_data igb_i2c_algo = {
+	.setsda		= igb_set_i2c_data,
+	.setscl		= igb_set_i2c_clk,
+	.getsda		= igb_get_i2c_data,
+	.getscl		= igb_get_i2c_clk,
+	.udelay		= 5,
+	.timeout	= 20,
+};
+
 /**
  * igb_get_hw_dev - return device
  * used by hardware layer to print debugging information
@@ -1708,6 +1797,18 @@ void igb_reset(struct igb_adapter *adapter)
 		igb_force_mac_fc(hw);
 
 	igb_init_dmac(adapter, pba);
+#ifdef CONFIG_IGB_HWMON
+	/* Re-initialize the thermal sensor on i350 devices. */
+	if (!test_bit(__IGB_DOWN, &adapter->state)) {
+		if (mac->type == e1000_i350 && hw->bus.func == 0) {
+			/* If present, re-initialize the external thermal sensor
+			 * interface.
+			 */
+			if (adapter->ets)
+				mac->ops.init_thermal_sensor_thresh(hw);
+		}
+	}
+#endif
 	if (!netif_running(adapter->netdev))
 		igb_power_down_link(adapter);
 
@@ -1822,6 +1923,37 @@ void igb_set_fw_version(struct igb_adapter *adapter)
 	return;
 }
 
+static const struct i2c_board_info i350_sensor_info = {
+	I2C_BOARD_INFO("i350bb", 0Xf8),
+};
+
+/*  igb_init_i2c - Init I2C interface
+ *  @adapter: pointer to adapter structure
+ *
+ */
+static s32 igb_init_i2c(struct igb_adapter *adapter)
+{
+	s32 status = E1000_SUCCESS;
+
+	/* I2C interface supported on i350 devices */
+	if (adapter->hw.mac.type != e1000_i350)
+		return E1000_SUCCESS;
+
+	/* Initialize the i2c bus which is controlled by the registers.
+	 * This bus will use the i2c_algo_bit structue that implements
+	 * the protocol through toggling of the 4 bits in the register.
+	 */
+	adapter->i2c_adap.owner = THIS_MODULE;
+	adapter->i2c_algo = igb_i2c_algo;
+	adapter->i2c_algo.data = adapter;
+	adapter->i2c_adap.algo_data = &adapter->i2c_algo;
+	adapter->i2c_adap.dev.parent = &adapter->pdev->dev;
+	strlcpy(adapter->i2c_adap.name, "igb BB",
+		sizeof(adapter->i2c_adap.name));
+	status = i2c_bit_add_bus(&adapter->i2c_adap);
+	return status;
+}
+
 /**
  * igb_probe - Device Initialization Routine
  * @pdev: PCI device information struct
@@ -2022,9 +2154,8 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 		dev_err(&pdev->dev, "NVM Read Error\n");
 
 	memcpy(netdev->dev_addr, hw->mac.addr, netdev->addr_len);
-	memcpy(netdev->perm_addr, hw->mac.addr, netdev->addr_len);
 
-	if (!is_valid_ether_addr(netdev->perm_addr)) {
+	if (!is_valid_ether_addr(netdev->dev_addr)) {
 		dev_err(&pdev->dev, "Invalid MAC Address\n");
 		err = -EIO;
 		goto err_eeprom;
@@ -2115,6 +2246,13 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* reset the hardware with the new settings */
 	igb_reset(adapter);
 
+	/* Init the I2C interface */
+	err = igb_init_i2c(adapter);
+	if (err) {
+		dev_err(&pdev->dev, "failed to init i2c interface\n");
+		goto err_eeprom;
+	}
+
 	/* let the f/w know that the h/w is now under the control of the
 	 * driver. */
 	igb_get_hw_control(adapter);
@@ -2135,7 +2273,27 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	}
 
 #endif
+#ifdef CONFIG_IGB_HWMON
+	/* Initialize the thermal sensor on i350 devices. */
+	if (hw->mac.type == e1000_i350 && hw->bus.func == 0) {
+		u16 ets_word;
 
+		/*
+		 * Read the NVM to determine if this i350 device supports an
+		 * external thermal sensor.
+		 */
+		hw->nvm.ops.read(hw, NVM_ETS_CFG, 1, &ets_word);
+		if (ets_word != 0x0000 && ets_word != 0xFFFF)
+			adapter->ets = true;
+		else
+			adapter->ets = false;
+		if (igb_sysfs_init(adapter))
+			dev_err(&pdev->dev,
+				"failed to allocate sysfs resources\n");
+	} else {
+		adapter->ets = false;
+	}
+#endif
 	/* do hw tstamp init after resetting */
 	igb_ptp_init(adapter);
 
@@ -2176,6 +2334,7 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 
 err_register:
 	igb_release_hw_control(adapter);
+	memset(&adapter->i2c_adap, 0, sizeof(adapter->i2c_adap));
 err_eeprom:
 	if (!igb_check_reset_block(hw))
 		igb_reset_phy(hw);
@@ -2196,6 +2355,111 @@ err_dma:
 	return err;
 }
 
+#ifdef CONFIG_PCI_IOV
+static int  igb_disable_sriov(struct pci_dev *pdev)
+{
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct igb_adapter *adapter = netdev_priv(netdev);
+	struct e1000_hw *hw = &adapter->hw;
+
+	/* reclaim resources allocated to VFs */
+	if (adapter->vf_data) {
+		/* disable iov and allow time for transactions to clear */
+		if (igb_vfs_are_assigned(adapter)) {
+			dev_warn(&pdev->dev,
+				 "Cannot deallocate SR-IOV virtual functions while they are assigned - VFs will not be deallocated\n");
+			return -EPERM;
+		} else {
+			pci_disable_sriov(pdev);
+			msleep(500);
+		}
+
+		kfree(adapter->vf_data);
+		adapter->vf_data = NULL;
+		adapter->vfs_allocated_count = 0;
+		wr32(E1000_IOVCTL, E1000_IOVCTL_REUSE_VFQ);
+		wrfl();
+		msleep(100);
+		dev_info(&pdev->dev, "IOV Disabled\n");
+
+		/* Re-enable DMA Coalescing flag since IOV is turned off */
+		adapter->flags |= IGB_FLAG_DMAC;
+	}
+
+	return 0;
+}
+
+static int igb_enable_sriov(struct pci_dev *pdev, int num_vfs)
+{
+	struct net_device *netdev = pci_get_drvdata(pdev);
+	struct igb_adapter *adapter = netdev_priv(netdev);
+	int old_vfs = pci_num_vf(pdev);
+	int err = 0;
+	int i;
+
+	if (!num_vfs)
+		goto out;
+	else if (old_vfs && old_vfs == num_vfs)
+		goto out;
+	else if (old_vfs && old_vfs != num_vfs)
+		err = igb_disable_sriov(pdev);
+
+	if (err)
+		goto out;
+
+	if (num_vfs > 7) {
+		err = -EPERM;
+		goto out;
+	}
+
+	adapter->vfs_allocated_count = num_vfs;
+
+	adapter->vf_data = kcalloc(adapter->vfs_allocated_count,
+				sizeof(struct vf_data_storage), GFP_KERNEL);
+
+	/* if allocation failed then we do not support SR-IOV */
+	if (!adapter->vf_data) {
+		adapter->vfs_allocated_count = 0;
+		dev_err(&pdev->dev,
+			"Unable to allocate memory for VF Data Storage\n");
+		err = -ENOMEM;
+		goto out;
+	}
+
+	err = pci_enable_sriov(pdev, adapter->vfs_allocated_count);
+	if (err)
+		goto err_out;
+
+	dev_info(&pdev->dev, "%d VFs allocated\n",
+		 adapter->vfs_allocated_count);
+	for (i = 0; i < adapter->vfs_allocated_count; i++)
+		igb_vf_configure(adapter, i);
+
+	/* DMA Coalescing is not supported in IOV mode. */
+	adapter->flags &= ~IGB_FLAG_DMAC;
+	goto out;
+
+err_out:
+	kfree(adapter->vf_data);
+	adapter->vf_data = NULL;
+	adapter->vfs_allocated_count = 0;
+out:
+	return err;
+}
+
+#endif
+/*
+ *  igb_remove_i2c - Cleanup  I2C interface
+ *  @adapter: pointer to adapter structure
+ *
+ */
+static void igb_remove_i2c(struct igb_adapter *adapter)
+{
+
+	/* free the adapter bus structure */
+	i2c_del_adapter(&adapter->i2c_adap);
+}
+
 /**
  * igb_remove - Device Removal Routine
  * @pdev: PCI device information struct
@@ -2212,8 +2476,11 @@ static void igb_remove(struct pci_dev *pdev)
 	struct e1000_hw *hw = &adapter->hw;
 
 	pm_runtime_get_noresume(&pdev->dev);
+#ifdef CONFIG_IGB_HWMON
+	igb_sysfs_exit(adapter);
+#endif
+	igb_remove_i2c(adapter);
 	igb_ptp_stop(adapter);
-
 	/*
 	 * The watchdog timer may be rescheduled, so explicitly
 	 * disable watchdog from being rescheduled.
@@ -2243,23 +2510,7 @@ static void igb_remove(struct pci_dev *pdev)
 	igb_clear_interrupt_scheme(adapter);
 
 #ifdef CONFIG_PCI_IOV
-	/* reclaim resources allocated to VFs */
-	if (adapter->vf_data) {
-		/* disable iov and allow time for transactions to clear */
-		if (igb_vfs_are_assigned(adapter)) {
-			dev_info(&pdev->dev, "Unloading driver while VFs are assigned - VFs will not be deallocated\n");
-		} else {
-			pci_disable_sriov(pdev);
-			msleep(500);
-		}
-
-		kfree(adapter->vf_data);
-		adapter->vf_data = NULL;
-		wr32(E1000_IOVCTL, E1000_IOVCTL_REUSE_VFQ);
-		wrfl();
-		msleep(100);
-		dev_info(&pdev->dev, "IOV Disabled\n");
-	}
+	igb_disable_sriov(pdev);
 #endif
 
 	iounmap(hw->hw_addr);
@@ -2290,103 +2541,22 @@ static void igb_probe_vfs(struct igb_adapter *adapter)
 #ifdef CONFIG_PCI_IOV
 	struct pci_dev *pdev = adapter->pdev;
 	struct e1000_hw *hw = &adapter->hw;
-	int old_vfs = pci_num_vf(adapter->pdev);
-	int i;
 
 	/* Virtualization features not supported on i210 family. */
 	if ((hw->mac.type == e1000_i210) || (hw->mac.type == e1000_i211))
 		return;
 
-	if (old_vfs) {
-		dev_info(&pdev->dev, "%d pre-allocated VFs found - override "
-			 "max_vfs setting of %d\n", old_vfs, max_vfs);
-		adapter->vfs_allocated_count = old_vfs;
-	}
-
-	if (!adapter->vfs_allocated_count)
-		return;
-
-	adapter->vf_data = kcalloc(adapter->vfs_allocated_count,
-				sizeof(struct vf_data_storage), GFP_KERNEL);
-
-	/* if allocation failed then we do not support SR-IOV */
-	if (!adapter->vf_data) {
-		adapter->vfs_allocated_count = 0;
-		dev_err(&pdev->dev, "Unable to allocate memory for VF "
-			"Data Storage\n");
-		goto out;
-	}
-
-	if (!old_vfs) {
-		if (pci_enable_sriov(pdev, adapter->vfs_allocated_count))
-			goto err_out;
-	}
-	dev_info(&pdev->dev, "%d VFs allocated\n",
-		 adapter->vfs_allocated_count);
-	for (i = 0; i < adapter->vfs_allocated_count; i++)
-		igb_vf_configure(adapter, i);
+	igb_enable_sriov(pdev, max_vfs);
+	pci_sriov_set_totalvfs(pdev, 7);
 
-	/* DMA Coalescing is not supported in IOV mode. */
-	adapter->flags &= ~IGB_FLAG_DMAC;
-	goto out;
-err_out:
-	kfree(adapter->vf_data);
-	adapter->vf_data = NULL;
-	adapter->vfs_allocated_count = 0;
-out:
-	return;
 #endif /* CONFIG_PCI_IOV */
 }
 
-/**
- * igb_sw_init - Initialize general software structures (struct igb_adapter)
- * @adapter: board private structure to initialize
- *
- * igb_sw_init initializes the Adapter private data structure.
- * Fields are initialized based on PCI device information and
- * OS network device settings (MTU size).
- **/
-static int igb_sw_init(struct igb_adapter *adapter)
+static void igb_init_queue_configuration(struct igb_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
-	struct net_device *netdev = adapter->netdev;
-	struct pci_dev *pdev = adapter->pdev;
 	u32 max_rss_queues;
 
-	pci_read_config_word(pdev, PCI_COMMAND, &hw->bus.pci_cmd_word);
-
-	/* set default ring sizes */
-	adapter->tx_ring_count = IGB_DEFAULT_TXD;
-	adapter->rx_ring_count = IGB_DEFAULT_RXD;
-
-	/* set default ITR values */
-	adapter->rx_itr_setting = IGB_DEFAULT_ITR;
-	adapter->tx_itr_setting = IGB_DEFAULT_ITR;
-
-	/* set default work limits */
-	adapter->tx_work_limit = IGB_DEFAULT_TX_WORK;
-
-	adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN +
-				  VLAN_HLEN;
-	adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
-
-	spin_lock_init(&adapter->stats64_lock);
-#ifdef CONFIG_PCI_IOV
-	switch (hw->mac.type) {
-	case e1000_82576:
-	case e1000_i350:
-		if (max_vfs > 7) {
-			dev_warn(&pdev->dev,
-				 "Maximum of 7 VFs per PF, using max\n");
-			adapter->vfs_allocated_count = 7;
-		} else
-			adapter->vfs_allocated_count = max_vfs;
-		break;
-	default:
-		break;
-	}
-#endif /* CONFIG_PCI_IOV */
-
 	/* Determine the maximum number of RSS queues supported. */
 	switch (hw->mac.type) {
 	case e1000_i211:
@@ -2445,11 +2615,64 @@ static int igb_sw_init(struct igb_adapter *adapter)
 			adapter->flags |= IGB_FLAG_QUEUE_PAIRS;
 		break;
 	}
+}
+
+/**
+ * igb_sw_init - Initialize general software structures (struct igb_adapter)
+ * @adapter: board private structure to initialize
+ *
+ * igb_sw_init initializes the Adapter private data structure.
+ * Fields are initialized based on PCI device information and
+ * OS network device settings (MTU size).
+ **/
+static int igb_sw_init(struct igb_adapter *adapter)
+{
+	struct e1000_hw *hw = &adapter->hw;
+	struct net_device *netdev = adapter->netdev;
+	struct pci_dev *pdev = adapter->pdev;
+
+	pci_read_config_word(pdev, PCI_COMMAND, &hw->bus.pci_cmd_word);
+
+	/* set default ring sizes */
+	adapter->tx_ring_count = IGB_DEFAULT_TXD;
+	adapter->rx_ring_count = IGB_DEFAULT_RXD;
+
+	/* set default ITR values */
+	adapter->rx_itr_setting = IGB_DEFAULT_ITR;
+	adapter->tx_itr_setting = IGB_DEFAULT_ITR;
+
+	/* set default work limits */
+	adapter->tx_work_limit = IGB_DEFAULT_TX_WORK;
+
+	adapter->max_frame_size = netdev->mtu + ETH_HLEN + ETH_FCS_LEN +
+				  VLAN_HLEN;
+	adapter->min_frame_size = ETH_ZLEN + ETH_FCS_LEN;
+
+	spin_lock_init(&adapter->stats64_lock);
+#ifdef CONFIG_PCI_IOV
+	switch (hw->mac.type) {
+	case e1000_82576:
+	case e1000_i350:
+		if (max_vfs > 7) {
+			dev_warn(&pdev->dev,
+				 "Maximum of 7 VFs per PF, using max\n");
+			adapter->vfs_allocated_count = 7;
+		} else
+			adapter->vfs_allocated_count = max_vfs;
+		if (adapter->vfs_allocated_count)
+			dev_warn(&pdev->dev,
+				 "Enabling SR-IOV VFs using the module parameter is deprecated - please use the pci sysfs interface.\n");
+		break;
+	default:
+		break;
+	}
+#endif /* CONFIG_PCI_IOV */
+
+	igb_init_queue_configuration(adapter);
 
 	/* Setup and initialize a copy of the hw vlan table array */
-	adapter->shadow_vfta = kzalloc(sizeof(u32) *
-				E1000_VLAN_FILTER_TBL_SIZE,
-				GFP_ATOMIC);
+	adapter->shadow_vfta = kcalloc(E1000_VLAN_FILTER_TBL_SIZE, sizeof(u32),
+				       GFP_ATOMIC);
 
 	/* This call may decrease the number of queues */
 	if (igb_init_interrupt_scheme(adapter, true)) {
@@ -3131,6 +3354,20 @@ void igb_configure_rx_ring(struct igb_adapter *adapter,
 	wr32(E1000_RXDCTL(reg_idx), rxdctl);
 }
 
+static void igb_set_rx_buffer_len(struct igb_adapter *adapter,
+				  struct igb_ring *rx_ring)
+{
+#define IGB_MAX_BUILD_SKB_SIZE \
+	(SKB_WITH_OVERHEAD(IGB_RX_BUFSZ) - \
+	 (NET_SKB_PAD + NET_IP_ALIGN + IGB_TS_HDR_LEN))
+
+	/* set build_skb flag */
+	if (adapter->max_frame_size <= IGB_MAX_BUILD_SKB_SIZE)
+		set_ring_build_skb_enabled(rx_ring);
+	else
+		clear_ring_build_skb_enabled(rx_ring);
+}
+
 /**
  * igb_configure_rx - Configure receive Unit after Reset
  * @adapter: board private structure
@@ -3150,8 +3387,11 @@ static void igb_configure_rx(struct igb_adapter *adapter)
 
 	/* Setup the HW Rx Head and Tail Descriptor Pointers and
 	 * the Base and Length of the Rx Descriptor Ring */
-	for (i = 0; i < adapter->num_rx_queues; i++)
-		igb_configure_rx_ring(adapter, adapter->rx_ring[i]);
+	for (i = 0; i < adapter->num_rx_queues; i++) {
+		struct igb_ring *rx_ring = adapter->rx_ring[i];
+		igb_set_rx_buffer_len(adapter, rx_ring);
+		igb_configure_rx_ring(adapter, rx_ring);
+	}
 }
 
 /**
@@ -3768,6 +4008,7 @@ static void igb_watchdog_task(struct work_struct *work)
 	}
 
 	igb_spoof_check(adapter);
+	igb_ptp_rx_hang(adapter);
 
 	/* Reset the timer */
 	if (!test_bit(__IGB_DOWN, &adapter->state))
@@ -4193,13 +4434,6 @@ static void igb_tx_olinfo_status(struct igb_ring *tx_ring,
 	tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
 }
 
-/*
- * The largest size we can write to the descriptor is 65535.  In order to
- * maintain a power of two alignment we have to limit ourselves to 32K.
- */
-#define IGB_MAX_TXD_PWR	15
-#define IGB_MAX_DATA_PER_TXD	(1<<IGB_MAX_TXD_PWR)
-
 static void igb_tx_map(struct igb_ring *tx_ring,
 		       struct igb_tx_buffer *first,
 		       const u8 hdr_len)
@@ -4368,15 +4602,25 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 	struct igb_tx_buffer *first;
 	int tso;
 	u32 tx_flags = 0;
+	u16 count = TXD_USE_COUNT(skb_headlen(skb));
 	__be16 protocol = vlan_get_protocol(skb);
 	u8 hdr_len = 0;
 
-	/* need: 1 descriptor per page,
+	/* need: 1 descriptor per page * PAGE_SIZE/IGB_MAX_DATA_PER_TXD,
+	 *       + 1 desc for skb_headlen/IGB_MAX_DATA_PER_TXD,
 	 *       + 2 desc gap to keep tail from touching head,
-	 *       + 1 desc for skb->data,
 	 *       + 1 desc for context descriptor,
-	 * otherwise try next time */
-	if (igb_maybe_stop_tx(tx_ring, skb_shinfo(skb)->nr_frags + 4)) {
+	 * otherwise try next time
+	 */
+	if (NETDEV_FRAG_PAGE_MAX_SIZE > IGB_MAX_DATA_PER_TXD) {
+		unsigned short f;
+		for (f = 0; f < skb_shinfo(skb)->nr_frags; f++)
+			count += TXD_USE_COUNT(skb_shinfo(skb)->frags[f].size);
+	} else {
+		count += skb_shinfo(skb)->nr_frags;
+	}
+
+	if (igb_maybe_stop_tx(tx_ring, count + 3)) {
 		/* this is a hard error */
 		return NETDEV_TX_BUSY;
 	}
@@ -4387,12 +4631,15 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 	first->bytecount = skb->len;
 	first->gso_segs = 1;
 
+	skb_tx_timestamp(skb);
+
 	if (unlikely((skb_shinfo(skb)->tx_flags & SKBTX_HW_TSTAMP) &&
 		     !(adapter->ptp_tx_skb))) {
 		skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS;
 		tx_flags |= IGB_TX_FLAGS_TSTAMP;
 
 		adapter->ptp_tx_skb = skb_get(skb);
+		adapter->ptp_tx_start = jiffies;
 		if (adapter->hw.mac.type == e1000_82576)
 			schedule_work(&adapter->ptp_tx_work);
 	}
@@ -4415,7 +4662,7 @@ netdev_tx_t igb_xmit_frame_ring(struct sk_buff *skb,
 	igb_tx_map(tx_ring, first, hdr_len);
 
 	/* Make sure there is space in the ring for the next send. */
-	igb_maybe_stop_tx(tx_ring, MAX_SKB_FRAGS + 4);
+	igb_maybe_stop_tx(tx_ring, DESC_NEEDED);
 
 	return NETDEV_TX_OK;
 
@@ -4969,7 +5216,7 @@ static int igb_vf_configure(struct igb_adapter *adapter, int vf)
 {
 	unsigned char mac_addr[ETH_ALEN];
 
-	eth_random_addr(mac_addr);
+	eth_zero_addr(mac_addr);
 	igb_set_vf_mac(adapter, vf, mac_addr);
 
 	return 0;
@@ -5322,9 +5569,9 @@ static void igb_vf_reset_event(struct igb_adapter *adapter, u32 vf)
 {
 	unsigned char *vf_mac = adapter->vf_data[vf].vf_mac_addresses;
 
-	/* generate a new mac address as we were hotplug removed/added */
+	/* clear mac address as we were hotplug removed/added */
 	if (!(adapter->vf_data[vf].flags & IGB_VF_FLAG_PF_SET_MAC))
-		eth_random_addr(vf_mac);
+		eth_zero_addr(vf_mac);
 
 	/* process remaining reset events */
 	igb_vf_reset(adapter, vf);
@@ -5703,7 +5950,7 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
 			break;
 
 		/* prevent any other reads prior to eop_desc */
-		rmb();
+		read_barrier_depends();
 
 		/* if DD is not set pending work has not been completed */
 		if (!(eop_desc->wb.status & cpu_to_le32(E1000_TXD_STAT_DD)))
@@ -5819,9 +6066,10 @@ static bool igb_clean_tx_irq(struct igb_q_vector *q_vector)
 		}
 	}
 
+#define TX_WAKE_THRESHOLD (DESC_NEEDED * 2)
 	if (unlikely(total_packets &&
 		     netif_carrier_ok(tx_ring->netdev) &&
-		     igb_desc_unused(tx_ring) >= IGB_TX_QUEUE_WAKE)) {
+		     igb_desc_unused(tx_ring) >= TX_WAKE_THRESHOLD)) {
 		/* Make sure that anybody stopping the queue after this
 		 * sees the new next_to_clean.
 		 */
@@ -5870,6 +6118,41 @@ static void igb_reuse_rx_page(struct igb_ring *rx_ring,
 					 DMA_FROM_DEVICE);
 }
 
+static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer,
+				  struct page *page,
+				  unsigned int truesize)
+{
+	/* avoid re-using remote pages */
+	if (unlikely(page_to_nid(page) != numa_node_id()))
+		return false;
+
+#if (PAGE_SIZE < 8192)
+	/* if we are only owner of page we can reuse it */
+	if (unlikely(page_count(page) != 1))
+		return false;
+
+	/* flip page offset to other buffer */
+	rx_buffer->page_offset ^= IGB_RX_BUFSZ;
+
+	/* since we are the only owner of the page and we need to
+	 * increment it, just set the value to 2 in order to avoid
+	 * an unnecessary locked operation
+	 */
+	atomic_set(&page->_count, 2);
+#else
+	/* move offset up to the next cache line */
+	rx_buffer->page_offset += truesize;
+
+	if (rx_buffer->page_offset > (PAGE_SIZE - IGB_RX_BUFSZ))
+		return false;
+
+	/* bump ref count on page before it is given to the stack */
+	get_page(page);
+#endif
+
+	return true;
+}
+
 /**
  * igb_add_rx_frag - Add contents of Rx buffer to sk_buff
  * @rx_ring: rx descriptor ring to transact packets on
@@ -5892,6 +6175,11 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring,
 {
 	struct page *page = rx_buffer->page;
 	unsigned int size = le16_to_cpu(rx_desc->wb.upper.length);
+#if (PAGE_SIZE < 8192)
+	unsigned int truesize = IGB_RX_BUFSZ;
+#else
+	unsigned int truesize = ALIGN(size, L1_CACHE_BYTES);
+#endif
 
 	if ((size <= IGB_RX_HDR_LEN) && !skb_is_nonlinear(skb)) {
 		unsigned char *va = page_address(page) + rx_buffer->page_offset;
@@ -5914,38 +6202,88 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring,
 	}
 
 	skb_add_rx_frag(skb, skb_shinfo(skb)->nr_frags, page,
-			rx_buffer->page_offset, size, IGB_RX_BUFSZ);
+			rx_buffer->page_offset, size, truesize);
 
-	/* avoid re-using remote pages */
-	if (unlikely(page_to_nid(page) != numa_node_id()))
-		return false;
+	return igb_can_reuse_rx_page(rx_buffer, page, truesize);
+}
 
+static struct sk_buff *igb_build_rx_buffer(struct igb_ring *rx_ring,
+					   union e1000_adv_rx_desc *rx_desc)
+{
+	struct igb_rx_buffer *rx_buffer;
+	struct sk_buff *skb;
+	struct page *page;
+	void *page_addr;
+	unsigned int size = le16_to_cpu(rx_desc->wb.upper.length);
 #if (PAGE_SIZE < 8192)
-	/* if we are only owner of page we can reuse it */
-	if (unlikely(page_count(page) != 1))
-		return false;
+	unsigned int truesize = IGB_RX_BUFSZ;
+#else
+	unsigned int truesize = SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) +
+				SKB_DATA_ALIGN(NET_SKB_PAD +
+					       NET_IP_ALIGN +
+					       size);
+#endif
 
-	/* flip page offset to other buffer */
-	rx_buffer->page_offset ^= IGB_RX_BUFSZ;
+	/* If we spanned a buffer we have a huge mess so test for it */
+	BUG_ON(unlikely(!igb_test_staterr(rx_desc, E1000_RXD_STAT_EOP)));
 
-	/*
-	 * since we are the only owner of the page and we need to
-	 * increment it, just set the value to 2 in order to avoid
-	 * an unnecessary locked operation
-	 */
-	atomic_set(&page->_count, 2);
-#else
-	/* move offset up to the next cache line */
-	rx_buffer->page_offset += SKB_DATA_ALIGN(size);
+	/* Guarantee this function can be used by verifying buffer sizes */
+	BUILD_BUG_ON(SKB_WITH_OVERHEAD(IGB_RX_BUFSZ) < (NET_SKB_PAD +
+							NET_IP_ALIGN +
+							IGB_TS_HDR_LEN +
+							ETH_FRAME_LEN +
+							ETH_FCS_LEN));
 
-	if (rx_buffer->page_offset > (PAGE_SIZE - IGB_RX_BUFSZ))
-		return false;
+	rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
+	page = rx_buffer->page;
+	prefetchw(page);
 
-	/* bump ref count on page before it is given to the stack */
-	get_page(page);
+	page_addr = page_address(page) + rx_buffer->page_offset;
+
+	/* prefetch first cache line of first page */
+	prefetch(page_addr + NET_SKB_PAD + NET_IP_ALIGN);
+#if L1_CACHE_BYTES < 128
+	prefetch(page_addr + L1_CACHE_BYTES + NET_SKB_PAD + NET_IP_ALIGN);
 #endif
 
-	return true;
+	/* build an skb to around the page buffer */
+	skb = build_skb(page_addr, truesize);
+	if (unlikely(!skb)) {
+		rx_ring->rx_stats.alloc_failed++;
+		return NULL;
+	}
+
+	/* we are reusing so sync this buffer for CPU use */
+	dma_sync_single_range_for_cpu(rx_ring->dev,
+				      rx_buffer->dma,
+				      rx_buffer->page_offset,
+				      IGB_RX_BUFSZ,
+				      DMA_FROM_DEVICE);
+
+	/* update pointers within the skb to store the data */
+	skb_reserve(skb, NET_IP_ALIGN + NET_SKB_PAD);
+	__skb_put(skb, size);
+
+	/* pull timestamp out of packet data */
+	if (igb_test_staterr(rx_desc, E1000_RXDADV_STAT_TSIP)) {
+		igb_ptp_rx_pktstamp(rx_ring->q_vector, skb->data, skb);
+		__skb_pull(skb, IGB_TS_HDR_LEN);
+	}
+
+	if (igb_can_reuse_rx_page(rx_buffer, page, truesize)) {
+		/* hand second half of page back to the ring */
+		igb_reuse_rx_page(rx_ring, rx_buffer);
+	} else {
+		/* we are not reusing the buffer so unmap it */
+		dma_unmap_page(rx_ring->dev, rx_buffer->dma,
+			       PAGE_SIZE, DMA_FROM_DEVICE);
+	}
+
+	/* clear contents of buffer_info */
+	rx_buffer->dma = 0;
+	rx_buffer->page = NULL;
+
+	return skb;
 }
 
 static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring,
@@ -5957,13 +6295,6 @@ static struct sk_buff *igb_fetch_rx_buffer(struct igb_ring *rx_ring,
 
 	rx_buffer = &rx_ring->rx_buffer_info[rx_ring->next_to_clean];
 
-	/*
-	 * This memory barrier is needed to keep us from reading
-	 * any other fields out of the rx_desc until we know the
-	 * RXD_STAT_DD bit is set
-	 */
-	rmb();
-
 	page = rx_buffer->page;
 	prefetchw(page);
 
@@ -6363,8 +6694,17 @@ static bool igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
 		if (!igb_test_staterr(rx_desc, E1000_RXD_STAT_DD))
 			break;
 
+		/* This memory barrier is needed to keep us from reading
+		 * any other fields out of the rx_desc until we know the
+		 * RXD_STAT_DD bit is set
+		 */
+		rmb();
+
 		/* retrieve a buffer from the ring */
-		skb = igb_fetch_rx_buffer(rx_ring, rx_desc, skb);
+		if (ring_uses_build_skb(rx_ring))
+			skb = igb_build_rx_buffer(rx_ring, rx_desc);
+		else
+			skb = igb_fetch_rx_buffer(rx_ring, rx_desc, skb);
 
 		/* exit if we failed to retrieve a buffer */
 		if (!skb)
@@ -6451,6 +6791,14 @@ static bool igb_alloc_mapped_page(struct igb_ring *rx_ring,
 	return true;
 }
 
+static inline unsigned int igb_rx_offset(struct igb_ring *rx_ring)
+{
+	if (ring_uses_build_skb(rx_ring))
+		return NET_SKB_PAD + NET_IP_ALIGN;
+	else
+		return 0;
+}
+
 /**
  * igb_alloc_rx_buffers - Replace used receive buffers; packet split
  * @adapter: address of board private structure
@@ -6477,7 +6825,9 @@ void igb_alloc_rx_buffers(struct igb_ring *rx_ring, u16 cleaned_count)
 		 * Refresh the desc even if buffer_addrs didn't change
 		 * because each write-back erases this info.
 		 */
-		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma + bi->page_offset);
+		rx_desc->read.pkt_addr = cpu_to_le64(bi->dma +
+						     bi->page_offset +
+						     igb_rx_offset(rx_ring));
 
 		rx_desc++;
 		bi++;
@@ -6903,6 +7253,72 @@ static void igb_shutdown(struct pci_dev *pdev)
 	}
 }
 
+#ifdef CONFIG_PCI_IOV
+static int igb_sriov_reinit(struct pci_dev *dev)
+{
+	struct net_device *netdev = pci_get_drvdata(dev);
+	struct igb_adapter *adapter = netdev_priv(netdev);
+	struct pci_dev *pdev = adapter->pdev;
+
+	rtnl_lock();
+
+	if (netif_running(netdev))
+		igb_close(netdev);
+
+	igb_clear_interrupt_scheme(adapter);
+
+	igb_init_queue_configuration(adapter);
+
+	if (igb_init_interrupt_scheme(adapter, true)) {
+		dev_err(&pdev->dev, "Unable to allocate memory for queues\n");
+		return -ENOMEM;
+	}
+
+	if (netif_running(netdev))
+		igb_open(netdev);
+
+	rtnl_unlock();
+
+	return 0;
+}
+
+static int igb_pci_disable_sriov(struct pci_dev *dev)
+{
+	int err = igb_disable_sriov(dev);
+
+	if (!err)
+		err = igb_sriov_reinit(dev);
+
+	return err;
+}
+
+static int igb_pci_enable_sriov(struct pci_dev *dev, int num_vfs)
+{
+	int err = igb_enable_sriov(dev, num_vfs);
+
+	if (err)
+		goto out;
+
+	err = igb_sriov_reinit(dev);
+	if (!err)
+		return num_vfs;
+
+out:
+	return err;
+}
+
+#endif
+static int igb_pci_sriov_configure(struct pci_dev *dev, int num_vfs)
+{
+#ifdef CONFIG_PCI_IOV
+	if (num_vfs == 0)
+		return igb_pci_disable_sriov(dev);
+	else
+		return igb_pci_enable_sriov(dev, num_vfs);
+#endif
+	return 0;
+}
+
 #ifdef CONFIG_NET_POLL_CONTROLLER
 /*
  * Polling 'interrupt' - used by things like netconsole to send skbs
@@ -7308,4 +7724,133 @@ static void igb_init_dmac(struct igb_adapter *adapter, u32 pba)
 	}
 }
 
+static DEFINE_SPINLOCK(i2c_clients_lock);
+
+/*  igb_get_i2c_client - returns matching client
+ *  in adapters's client list.
+ *  @adapter: adapter struct
+ *  @dev_addr: device address of i2c needed.
+ */
+static struct i2c_client *
+igb_get_i2c_client(struct igb_adapter *adapter, u8 dev_addr)
+{
+	ulong flags;
+	struct igb_i2c_client_list *client_list;
+	struct i2c_client *client = NULL;
+	struct i2c_board_info client_info = {
+		I2C_BOARD_INFO("igb", 0x00),
+	};
+
+	spin_lock_irqsave(&i2c_clients_lock, flags);
+	client_list = adapter->i2c_clients;
+
+	/* See if we already have an i2c_client */
+	while (client_list) {
+		if (client_list->client->addr == (dev_addr >> 1)) {
+			client = client_list->client;
+			goto exit;
+		} else {
+			client_list = client_list->next;
+		}
+	}
+
+	/* no client_list found, create a new one */
+	client_list = kzalloc(sizeof(*client_list), GFP_ATOMIC);
+	if (client_list == NULL)
+		goto exit;
+
+	/* dev_addr passed to us is left-shifted by 1 bit
+	 * i2c_new_device call expects it to be flush to the right.
+	 */
+	client_info.addr = dev_addr >> 1;
+	client_info.platform_data = adapter;
+	client_list->client = i2c_new_device(&adapter->i2c_adap, &client_info);
+	if (client_list->client == NULL) {
+		dev_info(&adapter->pdev->dev,
+			"Failed to create new i2c device..\n");
+		goto err_no_client;
+	}
+
+	/* insert new client at head of list */
+	client_list->next = adapter->i2c_clients;
+	adapter->i2c_clients = client_list;
+
+	client = client_list->client;
+	goto exit;
+
+err_no_client:
+	kfree(client_list);
+exit:
+	spin_unlock_irqrestore(&i2c_clients_lock, flags);
+	return client;
+}
+
+/*  igb_read_i2c_byte - Reads 8 bit word over I2C
+ *  @hw: pointer to hardware structure
+ *  @byte_offset: byte offset to read
+ *  @dev_addr: device address
+ *  @data: value read
+ *
+ *  Performs byte read operation over I2C interface at
+ *  a specified device address.
+ */
+s32 igb_read_i2c_byte(struct e1000_hw *hw, u8 byte_offset,
+				u8 dev_addr, u8 *data)
+{
+	struct igb_adapter *adapter = container_of(hw, struct igb_adapter, hw);
+	struct i2c_client *this_client = igb_get_i2c_client(adapter, dev_addr);
+	s32 status;
+	u16 swfw_mask = 0;
+
+	if (!this_client)
+		return E1000_ERR_I2C;
+
+	swfw_mask = E1000_SWFW_PHY0_SM;
+
+	if (hw->mac.ops.acquire_swfw_sync(hw, swfw_mask)
+	    != E1000_SUCCESS)
+		return E1000_ERR_SWFW_SYNC;
+
+	status = i2c_smbus_read_byte_data(this_client, byte_offset);
+	hw->mac.ops.release_swfw_sync(hw, swfw_mask);
+
+	if (status < 0)
+		return E1000_ERR_I2C;
+	else {
+		*data = status;
+		return E1000_SUCCESS;
+	}
+}
+
+/*  igb_write_i2c_byte - Writes 8 bit word over I2C
+ *  @hw: pointer to hardware structure
+ *  @byte_offset: byte offset to write
+ *  @dev_addr: device address
+ *  @data: value to write
+ *
+ *  Performs byte write operation over I2C interface at
+ *  a specified device address.
+ */
+s32 igb_write_i2c_byte(struct e1000_hw *hw, u8 byte_offset,
+				 u8 dev_addr, u8 data)
+{
+	struct igb_adapter *adapter = container_of(hw, struct igb_adapter, hw);
+	struct i2c_client *this_client = igb_get_i2c_client(adapter, dev_addr);
+	s32 status;
+	u16 swfw_mask = E1000_SWFW_PHY0_SM;
+
+	if (!this_client)
+		return E1000_ERR_I2C;
+
+	if (hw->mac.ops.acquire_swfw_sync(hw, swfw_mask) != E1000_SUCCESS)
+		return E1000_ERR_SWFW_SYNC;
+	status = i2c_smbus_write_byte_data(this_client, byte_offset, data);
+	hw->mac.ops.release_swfw_sync(hw, swfw_mask);
+
+	if (status)
+		return E1000_ERR_I2C;
+	else
+		return E1000_SUCCESS;
+
+}
 /* igb_main.c */